mysheet MCP Server
@lgwanai
About mysheet MCP Server
Mysheet-mcp is a MCP Server for converting Excel files into JSON format, particularly useful for data processing when called within large models or Agents.
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is mysheet MCP Server?
mysheet MCP Server is a Model Context Protocol server that converts Excel files into JSON format, with optional automatic uploading of embedded files to Tencent Cloud COS (Object Storage). It is designed for data processing within large language models or AI agents.
How to use mysheet MCP Server?
Install Java 21+ and Maven 3.6+, configure Tencent Cloud COS credentials and storage paths in application.yml, then start the server via ./mvnw spring-boot:run. The server exposes MCP tools (excel2Json, openFile, foreach, reset) that an AI agent can invoke to parse Excel files, manage sessions, and retrieve JSON data.
Key features of mysheet MCP Server
- Converts Excel files to JSON with detailed cell type information (text, number, money, date, file, boolean)
- Supports "row-object" parsing mode where each row becomes a JSON object
- Automatically uploads embedded files to Tencent Cloud COS and replaces local paths with COS URLs
- Uses Java 21 virtual threads for concurrent file uploads, boosting performance on large files
- Provides session management (
openFile,foreach,reset) for reading large Excel files in batches - Implements an MD5‑based cache to avoid re‑parsing identical files; cached data expires after 24 hours
Use cases of mysheet MCP Server
- Extracting structured data from Excel spreadsheets for LLM ingestion
- Processing Excel files that contain embedded images, documents, or other attachments stored on COS
- Handling large Excel files by reading rows in chunks through session‑based cursors
- Automating batch Excel‑to‑JSON conversion in AI agent workflows
FAQ from mysheet MCP Server
What Excel file formats are supported?
The server supports both .xls and .xlsx formats.
What are the runtime requirements?
Java 21 or higher (mandatory for virtual threads), Maven 3.6+, and a Tencent Cloud COS account for file storage.
How do I configure Tencent Cloud COS?
Edit src/main/resources/application.yml to set your COS secret‑id, secret‑key, region, and bucket‑name.
How does the cache work?
The server computes an MD5 hash of the uploaded Excel file and checks for a cached JSON file. If found, it returns the cached result. Cached session data is kept in memory for 24 hours and cleaned hourly.
What is the session timeout?
Sessions remain active in memory for 24 hours. The cleanup process runs every hour to remove expired sessions.
More Other MCP servers

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Inbox Zero AI MCP
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Core Philosophy: Connect, Unify, Respond
mindsdbDelegate anything. It comes back done.
Comments